Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to improvement, comparison, enhancement, or progression

    oai_token-act-pair · gpt-3.5-turbo

    terms related to measurement and comparative analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Marlins
    -0.61
    Els
    -0.61
     Hurricanes
    -0.60
    Orig
    -0.60
    PHOTOS
    -0.58
     awaited
    -0.58
     trench
    -0.57
     Zeit
    -0.56
     Orig
    -0.56
    mir
    -0.54
    POSITIVE LOGITS
    @#&
    0.75
    wcs
    0.69
    ilion
    0.68
    ctors
    0.67
    ealous
    0.66
    iciency
    0.66
    itt
    0.66
    ffect
    0.63
    iolet
    0.63
     Rhod
    0.63
    Act Density 0.510%

    No Known Activations